Lab 10 - ggplot

var_x <- 1:10
var_y <- 11:20

plot(var_x, var_y)

rand_sample <- sample(var_x, size = 100, replace = TRUE)
hist(rand_sample)

Grammar Of Graphics

• data
• aesthetic mapping
• geometric object
• statistical transformations
• scales
• coordinate system
• position adjustments
• faceting

Load package and data

library(tidyverse)

Registered S3 method overwritten by 'dplyr':
  method           from
  print.rowwise_df     
── Attaching packages ─────────────────────────────── tidyverse 1.2.1 ──
✔ ggplot2 3.2.1     ✔ purrr   0.3.2
✔ tibble  2.1.3     ✔ dplyr   0.8.3
✔ tidyr   0.8.3     ✔ stringr 1.4.0
✔ readr   1.3.1     ✔ forcats 0.4.0
── Conflicts ────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

data <- read_csv("plot_data.csv")

Parsed with column specification:
cols(
  Gene = col_character(),
  Length = col_double(),
  RPF = col_double(),
  mRNA = col_double(),
  uATG = col_logical(),
  Chromosome = col_character(),
  Size = col_double()
)

data

Structure of ggplot

Simple scatterplot

my_plot + 
  geom_point()

Changing scales of axes

my_plot +
  geom_point() +
  scale_x_continuous(trans = "log10") +
  scale_y_continuous(trans = "log10")

my_plot +
  geom_point() +
  scale_x_continuous(trans = "log2") +
  scale_y_continuous(trans = "log10")

my_plot +
  geom_point() +
  scale_x_continuous(trans = "log2")

Specify axis breakpoints

my_plot +
  geom_point() +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000))

Change limits and label styles of plots

my_plot +
  geom_point() +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000),
                     labels = scales::comma) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000),
                     labels = scales::comma)

my_plot +
  geom_point() +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000),
                     labels = scales::comma,
                     limits = c(1000, 25000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000),
                     labels = scales::comma,
                     limits = c(1000, 25000))

my_plot +
  geom_point() +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000, 25000),
                     labels = scales::comma,
                     limits = c(1000, 25000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000, 25000),
                     labels = scales::comma,
                     limits = c(1000, 25000))

Axis labels

my_plot +
  geom_point() +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot")

Changing transparency of points

my_plot +
  geom_point(alpha = 0.1) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot")

Color points

Color points with a variables (aesthetic mapping) - continuous scale

ggplot(data = data, aes(x = mRNA, y = RPF, color = Chromosome)) +
  geom_point(alpha = 0.4) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot")

ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG)) +
  geom_point(alpha = 0.4) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot")

Color points with a variables (aesthetic mapping) - discrete scale and color brewer

ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG)) +
  geom_point(alpha = 0.4) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  scale_color_brewer(palette = "Set1")

Change shapes of points

ggplot(data = data, aes(x = mRNA, y = RPF, shape = uATG, color = uATG)) +
  geom_point(alpha = 0.4) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  scale_color_brewer(palette = "Set1")

Change sizes of points

ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG)) +
  geom_point(alpha = 0.4, 
             size = 2) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  scale_color_brewer(palette = "Set1")

ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG, size = Size)) +
  geom_point(alpha = 0.4) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  scale_color_brewer(palette = "Set1")

ggplot(data = data, aes(x = mRNA, y = RPF, color = Size, shape = uATG)) +
  geom_point(alpha = 0.4) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  scale_color_gradient(low = "red", high = "blue")

Adding trendlines and regression lines

Statistical tests

library(ggpubr)

Loading required package: magrittr

Attaching package: ‘magrittr’

The following object is masked from ‘package:purrr’:

    set_names

The following object is masked from ‘package:tidyr’:

    extract

ggplot(data = data, aes(x = mRNA, y = RPF)) +
  geom_point(alpha = 0.4, 
             size = 2) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  stat_cor() + 
  geom_smooth(method = "lm")

ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG)) +
  geom_point(alpha = 0.4, 
             size = 2) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  scale_color_brewer(palette = "Set1") +
  stat_cor() +
  geom_smooth(method = "lm")

ggplot(data = data, aes(x = mRNA, y = RPF, color = Chromosome)) +
  geom_point(alpha = 0.4, 
             size = 2) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  stat_cor() +
  geom_smooth(method = "lm")

Separate panels

ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG)) +
  geom_point(alpha = 0.4, 
             size = 2) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  stat_cor() +
  geom_smooth(method = "lm") +
  facet_grid(.~uATG)

ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG)) +
  geom_point(alpha = 0.4, 
             size = 2) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  stat_cor() +
  geom_smooth(method = "lm") +
  facet_grid(uATG~.)

ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG)) +
  geom_point(alpha = 0.4, 
             size = 2) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  stat_cor() +
  geom_smooth(method = "lm") +
  facet_grid(.~Chromosome)

ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG)) +
  geom_point(alpha = 0.4, 
             size = 2) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  stat_cor() +
  geom_smooth(method = "lm") +
  facet_wrap(.~Chromosome)

Histograms

ggplot(data = data, aes(x = mRNA)) +
  geom_histogram() +
  scale_x_continuous(trans = "log10") +
  labs(x = "Yeast mRNA abundance", 
       y = "Frequency", 
       title = "Histogram")

ggplot(data = data, aes(x = mRNA)) +
  geom_histogram(bins = 100) +
  scale_x_continuous(trans = "log10") +
  labs(x = "Yeast mRNA abundance", 
       y = "Frequency", 
       title = "Histogram")

ggplot(data = data, aes(x = mRNA, color = uATG)) +
  geom_histogram(bins = 100) +
  scale_x_continuous(trans = "log10") +
  labs(x = "Yeast mRNA abundance", 
       y = "Frequency", 
       title = "Histogram")

ggplot(data = data, aes(x = mRNA, color = uATG)) +
  geom_histogram(bins = 100, position = "dodge") +
  scale_x_continuous(trans = "log10") +
  labs(x = "Yeast mRNA abundance", 
       y = "Frequency", 
       title = "Histogram")

Density plots

ggplot(data = data, aes(x = mRNA, fill = uATG)) +
  geom_density(alpha = 0.5) +
  scale_x_continuous(trans = "log10") +
  labs(x = "Yeast mRNA abundance", 
       y = "Frequency", 
       title = "Density plot") +
  scale_fill_brewer(palette = "Set1")

Multi-panel density plots

ggplot(data = data, aes(x = mRNA, fill = uATG)) +
  geom_density(alpha = 0.5) +
  scale_x_continuous(trans = "log10") +
  labs(x = "Yeast mRNA abundance", 
       y = "Frequency", 
       title = "Density plot") +
  scale_fill_brewer(palette = "Set1") +
  facet_wrap(~Chromosome)

Boxplots and Violin plots

ggplot(data = data, aes(x = uATG, y = mRNA, fill = uATG)) +
  geom_boxplot() +
  scale_y_continuous(trans = "log10") +
  labs(x = "uATGs", 
       y = "Yeast mRNA abundance", 
       title = "Boxplot") +
  scale_fill_brewer(palette = "Set1")

ggplot(data = data, aes(x = uATG, y = mRNA, fill = uATG)) +
  geom_boxplot() +
  scale_y_continuous(trans = "log10") +
  labs(x = "uATGs", 
       y = "Yeast mRNA abundance", 
       title = "Boxplot") +
  scale_fill_brewer(palette = "Set1") +
  stat_compare_means(method = "t.test")

my_comparisons <- list(c("Chr-1", "Chr-2"),
                       c("Chr-1", "Chr-9"))

ggplot(data = data, aes(x = Chromosome, y = mRNA, fill = Chromosome)) +
  geom_boxplot() +
  scale_y_continuous(trans = "log10") +
  labs(x = "uATGs", 
       y = "Yeast mRNA abundance", 
       title = "Boxplot") +
  stat_compare_means(comparisons = my_comparisons, method = "t.test")

my_comparisons <- list(c("Chr-1", "Chr-2"),
                       c("Chr-1", "Chr-9"))

ggplot(data = data, aes(x = Chromosome, y = mRNA, fill = Chromosome)) +
  geom_violin() +
  scale_y_continuous(trans = "log10") +
  labs(x = "uATGs", 
       y = "Yeast mRNA abundance", 
       title = "Violin plot") +
  stat_compare_means(comparisons = my_comparisons, method = "t.test")

Boxplots with scatter points

ggplot(data = data, aes(x = uATG, y = mRNA, fill = uATG)) +
  geom_boxplot() +
  scale_y_continuous(trans = "log10") +
  labs(x = "uATGs", 
       y = "Yeast mRNA abundance", 
       title = "Boxplot") +
  scale_fill_brewer(palette = "Set1") +
  stat_compare_means(method = "t.test") +
  geom_jitter(alpha = 0.3, width = 0.1, height = 0)

Saving plots

myboxplot <- ggplot(data = data, aes(x = uATG, y = mRNA, fill = uATG)) +
  geom_boxplot() +
  scale_y_continuous(trans = "log10") +
  labs(x = "uATGs", 
       y = "Yeast mRNA abundance", 
       title = "Boxplot") +
  scale_fill_brewer(palette = "Set1") +
  stat_compare_means(method = "t.test") +
  geom_jitter(alpha = 0.3, width = 0.1, height = 0)

ggsave(myboxplot, filename = "myboxplot.png")

Saving 7 x 7 in image

Interactive plots

myscatterplot <- ggplot(data = data, aes(x = mRNA, y = RPF, color = uATG, label = Gene)) +
  geom_point(alpha = 0.4, 
             size = 2) +
  scale_x_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  scale_y_continuous(trans = "log10",
                     breaks = c(1, 5, 10, 50, 100, 500, 1000, 5000, 10000)) +
  labs(x = "Yeast mRNA abundance", 
       y = "Yeast RPF abundance", 
       title = "Scatterplot") +
  scale_color_brewer(palette = "Set1") +
  stat_cor() +
  geom_smooth(method = "lm")

library(plotly)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

ggplotly(myscatterplot)

Themes

myscatterplot +
  theme_pubr()